A graph-matching kernel for object categorization
This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions du...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1799 |
|---|---|
| container_issue | |
| container_start_page | 1792 |
| container_title | |
| container_volume | |
| creator | Duchenne, O. Joulin, A. Ponce, J. |
| description | This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions during matching. A fast approximate algorithm for matching the graphs associated with two images is presented. This algorithm is used to construct a kernel appropriate for SVM-based image classification, and experiments with the Caltech 101, Caltech 256, and Scenes datasets demonstrate performance that matches or exceeds the state of the art for methods using a single type of features. |
| doi_str_mv | 10.1109/ICCV.2011.6126445 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6126445</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6126445</ieee_id><sourcerecordid>6126445</sourcerecordid><originalsourceid>FETCH-LOGICAL-i241t-6e2ee882b74f68a506718487eee694f9b381442c60e0464f8fdabbdb7c19ed403</originalsourceid><addsrcrecordid>eNo1j8lOw0AQRIdNwgn5AMTFP2DTPe7ZjpHFEikSF-Aaje0eZ0ISR7Yv8PVYIpzq8FRPVULcI-SI4B5XZfmZS0DMNUpNpC7EDEkZM1HAS5HIwkJmFNCVWDhj_xmqa5GgUpApcu5WzIZhB1A4aXUicJm2vT9ts4Mf6208tukX90fep6Hr067acT2mtR-57fr448fYHe_ETfD7gRfnnIuP56f38jVbv72syuU6i5JwzDRLZmtlZSho6xVog5asYWbtKLiqmAaSrDUwkKZgQ-OrqqlMjY4bgmIuHv68capsTn08-P57c75e_AL4z0fg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A graph-matching kernel for object categorization</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Duchenne, O. ; Joulin, A. ; Ponce, J.</creator><creatorcontrib>Duchenne, O. ; Joulin, A. ; Ponce, J.</creatorcontrib><description>This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions during matching. A fast approximate algorithm for matching the graphs associated with two images is presented. This algorithm is used to construct a kernel appropriate for SVM-based image classification, and experiments with the Caltech 101, Caltech 256, and Scenes datasets demonstrate performance that matches or exceeds the state of the art for methods using a single type of features.</description><identifier>ISSN: 1550-5499</identifier><identifier>ISBN: 9781457711015</identifier><identifier>ISBN: 145771101X</identifier><identifier>EISSN: 2380-7504</identifier><identifier>EISBN: 1457711001</identifier><identifier>EISBN: 1457711028</identifier><identifier>EISBN: 9781457711022</identifier><identifier>EISBN: 9781457711008</identifier><identifier>DOI: 10.1109/ICCV.2011.6126445</identifier><language>eng</language><publisher>IEEE</publisher><subject>Approximation algorithms ; Image edge detection ; Image retrieval ; Kernel ; Optimization ; Support vector machines ; Vectors</subject><ispartof>2011 International Conference on Computer Vision, 2011, p.1792-1799</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6126445$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6126445$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Duchenne, O.</creatorcontrib><creatorcontrib>Joulin, A.</creatorcontrib><creatorcontrib>Ponce, J.</creatorcontrib><title>A graph-matching kernel for object categorization</title><title>2011 International Conference on Computer Vision</title><addtitle>ICCV</addtitle><description>This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions during matching. A fast approximate algorithm for matching the graphs associated with two images is presented. This algorithm is used to construct a kernel appropriate for SVM-based image classification, and experiments with the Caltech 101, Caltech 256, and Scenes datasets demonstrate performance that matches or exceeds the state of the art for methods using a single type of features.</description><subject>Approximation algorithms</subject><subject>Image edge detection</subject><subject>Image retrieval</subject><subject>Kernel</subject><subject>Optimization</subject><subject>Support vector machines</subject><subject>Vectors</subject><issn>1550-5499</issn><issn>2380-7504</issn><isbn>9781457711015</isbn><isbn>145771101X</isbn><isbn>1457711001</isbn><isbn>1457711028</isbn><isbn>9781457711022</isbn><isbn>9781457711008</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1j8lOw0AQRIdNwgn5AMTFP2DTPe7ZjpHFEikSF-Aaje0eZ0ISR7Yv8PVYIpzq8FRPVULcI-SI4B5XZfmZS0DMNUpNpC7EDEkZM1HAS5HIwkJmFNCVWDhj_xmqa5GgUpApcu5WzIZhB1A4aXUicJm2vT9ts4Mf6208tukX90fep6Hr067acT2mtR-57fr448fYHe_ETfD7gRfnnIuP56f38jVbv72syuU6i5JwzDRLZmtlZSho6xVog5asYWbtKLiqmAaSrDUwkKZgQ-OrqqlMjY4bgmIuHv68capsTn08-P57c75e_AL4z0fg</recordid><startdate>201111</startdate><enddate>201111</enddate><creator>Duchenne, O.</creator><creator>Joulin, A.</creator><creator>Ponce, J.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201111</creationdate><title>A graph-matching kernel for object categorization</title><author>Duchenne, O. ; Joulin, A. ; Ponce, J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i241t-6e2ee882b74f68a506718487eee694f9b381442c60e0464f8fdabbdb7c19ed403</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Approximation algorithms</topic><topic>Image edge detection</topic><topic>Image retrieval</topic><topic>Kernel</topic><topic>Optimization</topic><topic>Support vector machines</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Duchenne, O.</creatorcontrib><creatorcontrib>Joulin, A.</creatorcontrib><creatorcontrib>Ponce, J.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Duchenne, O.</au><au>Joulin, A.</au><au>Ponce, J.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A graph-matching kernel for object categorization</atitle><btitle>2011 International Conference on Computer Vision</btitle><stitle>ICCV</stitle><date>2011-11</date><risdate>2011</risdate><spage>1792</spage><epage>1799</epage><pages>1792-1799</pages><issn>1550-5499</issn><eissn>2380-7504</eissn><isbn>9781457711015</isbn><isbn>145771101X</isbn><eisbn>1457711001</eisbn><eisbn>1457711028</eisbn><eisbn>9781457711022</eisbn><eisbn>9781457711008</eisbn><abstract>This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions during matching. A fast approximate algorithm for matching the graphs associated with two images is presented. This algorithm is used to construct a kernel appropriate for SVM-based image classification, and experiments with the Caltech 101, Caltech 256, and Scenes datasets demonstrate performance that matches or exceeds the state of the art for methods using a single type of features.</abstract><pub>IEEE</pub><doi>10.1109/ICCV.2011.6126445</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1550-5499 |
| ispartof | 2011 International Conference on Computer Vision, 2011, p.1792-1799 |
| issn | 1550-5499 2380-7504 |
| language | eng |
| recordid | cdi_ieee_primary_6126445 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Approximation algorithms Image edge detection Image retrieval Kernel Optimization Support vector machines Vectors |
| title | A graph-matching kernel for object categorization |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T17%3A21%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20graph-matching%20kernel%20for%20object%20categorization&rft.btitle=2011%20International%20Conference%20on%20Computer%20Vision&rft.au=Duchenne,%20O.&rft.date=2011-11&rft.spage=1792&rft.epage=1799&rft.pages=1792-1799&rft.issn=1550-5499&rft.eissn=2380-7504&rft.isbn=9781457711015&rft.isbn_list=145771101X&rft_id=info:doi/10.1109/ICCV.2011.6126445&rft_dat=%3Cieee_6IE%3E6126445%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1457711001&rft.eisbn_list=1457711028&rft.eisbn_list=9781457711022&rft.eisbn_list=9781457711008&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6126445&rfr_iscdi=true |